A symbolic controller based intelligent control system with quantum particle swarm optimization based hybrid genetic algorithm

In this paper, a new symbolic controller based intelligent control system is proposed, namely gSyICS, which consists of a symbolic controller, a percepter, and a gAdaptor. The symbolic controller is made up of a number of symbolic rules. The percepter is to detect the control efficiency. Once the sensory information is inefficient or inadaptable, the gAdaptor will be activated; otherwise, the symbolic controller will keep on the controlling assignments. The gAdaptor consisted of the exploration process and symbolic rule generator is firstly to explore the new control actions, and then transforms them into new symbolic rules to update the rule base. The improved hybrid genetic algorithm is proposed to implement the exploration process for searching new actions, namely gHGA. A quantum behavior inspired particle swarm optimization that has the variable-length particles with discrete encoding is proposed to generate the partial initial population of gHGA. An application of robotic path planning is applied to demonstrate the proposed method through comparing with other methods. The simulation results showed that the proposed approach is more efficient than the other approaches.